Rethinking Memory Design in SAM-Based Visual Object Tracking

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Alansari, Mohamad, Naseer, Muzammal, Marzouqi, Hasan Al, Werghi, Naoufel, Javed, Sajid
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917172298645504
author Alansari, Mohamad
Naseer, Muzammal
Marzouqi, Hasan Al
Werghi, Naoufel
Javed, Sajid
author_facet Alansari, Mohamad
Naseer, Muzammal
Marzouqi, Hasan Al
Werghi, Naoufel
Javed, Sajid
contents \noindent Memory has become the central mechanism enabling robust visual object tracking in modern segmentation-based frameworks. Recent methods built upon Segment Anything Model 2 (SAM2) have demonstrated strong performance by refining how past observations are stored and reused. However, existing approaches address memory limitations in a method-specific manner, leaving the broader design principles of memory in SAM-based tracking poorly understood. Moreover, it remains unclear how these memory mechanisms transfer to stronger, next-generation foundation models such as Segment Anything Model 3 (SAM3). In this work, we present a systematic memory-centric study of SAM-based visual object tracking. We first analyze representative SAM2-based trackers and show that most methods primarily differ in how short-term memory frames are selected, while sharing a common object-centric representation. Building on this insight, we faithfully reimplement these memory mechanisms within the SAM3 framework and conduct large-scale evaluations across ten diverse benchmarks, enabling a controlled analysis of memory design independent of backbone strength. Guided by our empirical findings, we propose a unified hybrid memory framework that explicitly decomposes memory into short-term appearance memory and long-term distractor-resolving memory. This decomposition enables the integration of existing memory policies in a modular and principled manner. Extensive experiments demonstrate that the proposed framework consistently improves robustness under long-term occlusion, complex motion, and distractor-heavy scenarios on both SAM2 and SAM3 backbones. Code is available at: https://github.com/HamadYA/SAM3_Tracking_Zoo. \textbf{This is a preprint. Some results are being finalized and may be updated in a future revision.}
format Preprint
id arxiv_https___arxiv_org_abs_2512_22624
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rethinking Memory Design in SAM-Based Visual Object Tracking
Alansari, Mohamad
Naseer, Muzammal
Marzouqi, Hasan Al
Werghi, Naoufel
Javed, Sajid
Computer Vision and Pattern Recognition
\noindent Memory has become the central mechanism enabling robust visual object tracking in modern segmentation-based frameworks. Recent methods built upon Segment Anything Model 2 (SAM2) have demonstrated strong performance by refining how past observations are stored and reused. However, existing approaches address memory limitations in a method-specific manner, leaving the broader design principles of memory in SAM-based tracking poorly understood. Moreover, it remains unclear how these memory mechanisms transfer to stronger, next-generation foundation models such as Segment Anything Model 3 (SAM3). In this work, we present a systematic memory-centric study of SAM-based visual object tracking. We first analyze representative SAM2-based trackers and show that most methods primarily differ in how short-term memory frames are selected, while sharing a common object-centric representation. Building on this insight, we faithfully reimplement these memory mechanisms within the SAM3 framework and conduct large-scale evaluations across ten diverse benchmarks, enabling a controlled analysis of memory design independent of backbone strength. Guided by our empirical findings, we propose a unified hybrid memory framework that explicitly decomposes memory into short-term appearance memory and long-term distractor-resolving memory. This decomposition enables the integration of existing memory policies in a modular and principled manner. Extensive experiments demonstrate that the proposed framework consistently improves robustness under long-term occlusion, complex motion, and distractor-heavy scenarios on both SAM2 and SAM3 backbones. Code is available at: https://github.com/HamadYA/SAM3_Tracking_Zoo. \textbf{This is a preprint. Some results are being finalized and may be updated in a future revision.}
title Rethinking Memory Design in SAM-Based Visual Object Tracking
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.22624